TY - GEN
T1 - Towards Explainable Image Classifier
T2 - 2021 13th International Conference on Machine Learning and Computing, ICMLC 2021
AU - Seo, Yian
AU - Shin, Kyung Shik
N1 - Publisher Copyright:
© 2021 ACM.
PY - 2021/2/26
Y1 - 2021/2/26
N2 - With increased interests in Explainable Artificial Intelligence (XAI), many researches find ways to provide explanations for machine learning algorithms and their predictions. We propose Multiple Choice Questioned Convolutional Neural Network (MCQ-CNN) to better understand the prediction of image classifier by considering the problem of multi-class classification as the problem of multiple choice question. MCQ-CNN not only performs classification of the query image, but also explains the classification result by demonstrating the elimination process of multi-class labels in patch-level. The proposed model consists of two modules. Classification module is to classify class label of the query. Elimination module is to perform similarity measure in patch-level to distinguish whether the target object part shares the feature of certain class label or not. Classification module is trained using ResNet with high classification accuracy. Elimination module performs similarity measure by distance metric learning based on Large Margin Nearest Neighbor (LMNN). Our experiments have shown notable performances in both classification and elimination modules.
AB - With increased interests in Explainable Artificial Intelligence (XAI), many researches find ways to provide explanations for machine learning algorithms and their predictions. We propose Multiple Choice Questioned Convolutional Neural Network (MCQ-CNN) to better understand the prediction of image classifier by considering the problem of multi-class classification as the problem of multiple choice question. MCQ-CNN not only performs classification of the query image, but also explains the classification result by demonstrating the elimination process of multi-class labels in patch-level. The proposed model consists of two modules. Classification module is to classify class label of the query. Elimination module is to perform similarity measure in patch-level to distinguish whether the target object part shares the feature of certain class label or not. Classification module is trained using ResNet with high classification accuracy. Elimination module performs similarity measure by distance metric learning based on Large Margin Nearest Neighbor (LMNN). Our experiments have shown notable performances in both classification and elimination modules.
KW - Convolutional Neural Network
KW - Distance metric learning
KW - Explainable model
KW - Image classification
KW - Multiple Choice Question
UR - http://www.scopus.com/inward/record.url?scp=85109219336&partnerID=8YFLogxK
U2 - 10.1145/3457682.3457730
DO - 10.1145/3457682.3457730
M3 - Conference contribution
AN - SCOPUS:85109219336
T3 - ACM International Conference Proceeding Series
SP - 310
EP - 317
BT - 2021 13th International Conference on Machine Learning and Computing, ICMLC 2021
PB - Association for Computing Machinery
Y2 - 26 February 2021 through 1 March 2021
ER -